Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1628 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0002

Data Index: 142610 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0899. Min Act: -0.0002

Data Index: 733881 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0856. Min Act: -0.0002

Data Index: 394285 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1068976 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0881. Min Act: -0.0002

Data Index: 85452 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0867. Min Act: -0.0002

Data Index: 644965 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0796. Min Act: -0.0002

Data Index: 925967 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0801. Min Act: -0.0002

Data Index: 369188 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0794. Min Act: -0.0002

Data Index: 507717 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1011260 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1180635 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0689. Min Act: -0.0002

Data Index: 624335 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0651. Min Act: -0.0002

Data Index: 311866 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0673. Min Act: -0.0002

Data Index: 95705 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1043260 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0597. Min Act: -0.0002

Data Index: 797316 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0652. Min Act: -0.0002

Data Index: 521395 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0628. Min Act: -0.0002

Data Index: 313367 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1130176 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0584. Min Act: -0.0002

Data Index: 796396 (C4 (Web Text))

Max Activating Token Index: 752